Compare commits

...

2 Commits

Author SHA1 Message Date
Francis Couture-Harpin
ba06b2deb7 tokenize : add --no-parse-special option
This should allow more easily explaining
how parse_special affects tokenization.
2024-07-10 18:06:25 -04:00
Clint Herron
dd07a123b7 Name Migration: Build the deprecation-warning 'main' binary every time (#8404)
Some checks failed
Publish Docker image / Push Docker image to Docker Hub (map[dockerfile:.devops/full-cuda.Dockerfile platforms:linux/amd64 tag:full-cuda]) (push) Waiting to run
Publish Docker image / Push Docker image to Docker Hub (map[dockerfile:.devops/full.Dockerfile platforms:linux/amd64,linux/arm64 tag:full]) (push) Waiting to run
Publish Docker image / Push Docker image to Docker Hub (map[dockerfile:.devops/llama-cli-cuda.Dockerfile platforms:linux/amd64 tag:light-cuda]) (push) Waiting to run
Publish Docker image / Push Docker image to Docker Hub (map[dockerfile:.devops/llama-cli-intel.Dockerfile platforms:linux/amd64 tag:light-intel]) (push) Waiting to run
Publish Docker image / Push Docker image to Docker Hub (map[dockerfile:.devops/llama-cli-rocm.Dockerfile platforms:linux/amd64,linux/arm64 tag:light-rocm]) (push) Waiting to run
Publish Docker image / Push Docker image to Docker Hub (map[dockerfile:.devops/llama-cli.Dockerfile platforms:linux/amd64,linux/arm64 tag:light]) (push) Waiting to run
Publish Docker image / Push Docker image to Docker Hub (map[dockerfile:.devops/llama-server-cuda.Dockerfile platforms:linux/amd64 tag:server-cuda]) (push) Waiting to run
Publish Docker image / Push Docker image to Docker Hub (map[dockerfile:.devops/llama-server-intel.Dockerfile platforms:linux/amd64 tag:server-intel]) (push) Waiting to run
Publish Docker image / Push Docker image to Docker Hub (map[dockerfile:.devops/llama-server-rocm.Dockerfile platforms:linux/amd64,linux/arm64 tag:server-rocm]) (push) Waiting to run
Publish Docker image / Push Docker image to Docker Hub (map[dockerfile:.devops/llama-server.Dockerfile platforms:linux/amd64,linux/arm64 tag:server]) (push) Waiting to run
Nix CI / nix-eval (macos-latest) (push) Waiting to run
Nix CI / nix-eval (ubuntu-latest) (push) Waiting to run
Nix CI / nix-build (macos-latest) (push) Waiting to run
Nix CI / nix-build (ubuntu-latest) (push) Waiting to run
flake8 Lint / Lint (push) Waiting to run
Python check requirements.txt / check-requirements (push) Has been cancelled
Python Type-Check / pyright type-check (push) Has been cancelled
* Modify the deprecation-warning 'main' binary to build every time, instead of only when a legacy binary is present. This is to help users of tutorials and other instruction sets from knowing what to do when the 'main' binary is missing and they are trying to follow instructions.

* Adjusting 'server' name-deprecation binary to build all the time, similar to the 'main' legacy name binary.
2024-07-10 12:35:18 -04:00
2 changed files with 15 additions and 17 deletions

View File

@@ -1513,15 +1513,17 @@ llama-q8dot: pocs/vdot/q8dot.cpp ggml/src/ggml.o \
# Mark legacy binary targets as .PHONY so that they are always checked.
.PHONY: main quantize perplexity embedding server finetune
# NOTE: We currently will always build the deprecation-warning `main` and `server` binaries to help users migrate.
# Eventually we will want to remove these target from building all the time.
main: examples/deprecation-warning/deprecation-warning.cpp
ifneq (,$(wildcard main))
$(CXX) $(CXXFLAGS) -c $< -o $(call GET_OBJ_FILE, $<)
$(CXX) $(CXXFLAGS) $(filter-out $<,$^) $(call GET_OBJ_FILE, $<) -o $@ $(LDFLAGS)
@echo "#########"
@echo "WARNING: The 'main' binary is deprecated. Please use 'llama-cli' instead."
@echo " Remove the 'main' binary to remove this warning."
@echo "#########"
endif
@echo "NOTICE: The 'main' binary is deprecated. Please use 'llama-cli' instead."
server: examples/deprecation-warning/deprecation-warning.cpp
$(CXX) $(CXXFLAGS) -c $< -o $(call GET_OBJ_FILE, $<)
$(CXX) $(CXXFLAGS) $(filter-out %.h $<,$^) $(call GET_OBJ_FILE, $<) -o $@ $(LDFLAGS)
@echo "NOTICE: The 'server' binary is deprecated. Please use 'llama-server' instead."
quantize: examples/deprecation-warning/deprecation-warning.cpp
ifneq (,$(wildcard quantize))
@@ -1553,16 +1555,6 @@ ifneq (,$(wildcard embedding))
@echo "#########"
endif
server: examples/deprecation-warning/deprecation-warning.cpp
ifneq (,$(wildcard server))
$(CXX) $(CXXFLAGS) -c $< -o $(call GET_OBJ_FILE, $<)
$(CXX) $(CXXFLAGS) $(filter-out %.h $<,$^) $(call GET_OBJ_FILE, $<) -o $@ $(LDFLAGS)
@echo "#########"
@echo "WARNING: The 'server' binary is deprecated. Please use 'llama-server' instead."
@echo " Remove the 'server' binary to remove this warning."
@echo "#########"
endif
finetune: examples/deprecation-warning/deprecation-warning.cpp
ifneq (,$(wildcard finetune))
$(CXX) $(CXXFLAGS) -c $< -o $(call GET_OBJ_FILE, $<)

View File

@@ -29,6 +29,7 @@ static void print_usage_information(const char * argv0, FILE * stream) {
fprintf(stream, " -p PROMPT, --prompt PROMPT read prompt from the argument.\n");
fprintf(stream, " --stdin read prompt from standard input.\n");
fprintf(stream, " --no-bos do not ever add a BOS token to the prompt, even if normally the model uses a BOS token.\n");
fprintf(stream, " --no-parse-special do not parse control tokens.\n");
fprintf(stream, " --log-disable disable logs. Makes stderr quiet when loading the model.\n");
fprintf(stream, " --show-count print the total number of tokens.\n");
}
@@ -195,6 +196,7 @@ int main(int raw_argc, char ** raw_argv) {
// variables where to put any arguments we see.
bool printing_ids = false;
bool no_bos = false;
bool no_parse_special = false;
bool disable_logging = false;
bool show_token_count = false;
const char * model_path = NULL;
@@ -229,6 +231,9 @@ int main(int raw_argc, char ** raw_argv) {
else if (arg == "--no-bos") {
no_bos = true;
}
else if (arg == "--no-parse-special") {
no_parse_special = true;
}
else if (arg == "-p" || arg == "--prompt") {
if (prompt_set) {
fprintf(stderr, "Error: -p or --prompt specified multiple times.\n");
@@ -359,9 +364,10 @@ int main(int raw_argc, char ** raw_argv) {
const bool model_wants_add_bos = llama_should_add_bos_token(model);
const bool add_bos = model_wants_add_bos && !no_bos;
const bool parse_special = !no_parse_special;
std::vector<llama_token> tokens;
tokens = ::llama_tokenize(model, prompt, add_bos, true);
tokens = ::llama_tokenize(model, prompt, add_bos, parse_special);
if (printing_ids) {
printf("[");